Nikos Karampatziakis's repositories
secondorderdemos
second order demos
hkbu-benchmark
A git repository containing the scripts used in http://arxiv.org/abs/1608.07249
cntk-deepmark
CNTK implementations of deepmark benchmarks
vowpal_wabbit
John Langford's original release of Vowpal Wabbit -- a fast online learning algorithm
batch_rl
Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games
DALL-E
PyTorch package for the discrete VAE used for DALL·E.
dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
fastbook
Draft of the fastai book
muzero-general
MuZero
off-policy-confidence-sequences
off-policy confidence sequences
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
PoSE
Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length
SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.
SWE-bench
[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.